NVIDIA Jetson Orin NX- SoM Overview

From RidgeRun Developer Wiki


Previous: Introduction Index Next: Introduction/Carrier Boards







This section provides an overview of the Orin NX SoM components and their capabilities.


The NVIDIA Jetson Orin NX is a powerful SoM that provides on-edge AI capabilities featuring an NVIDIA Orin SoC version designed for low-power consumption (down to 10W).


Figure 1: NVIDIA Jetson Orin AGX SOM



Table 1 shows a summary of the hardware characteristics of the SoM:


Table 1: NVIDIA Jetson Orin NX SoM - Hardware Summary
Feature Jetson Orin NX 8GB Jetson Orin NX 16GB
AI Performance 70 Sparse TOPS (INT8) and 35 Dense TOPS (INT8) 100 Sparse TOPS (INT8) and 50 Dense TOPS (INT8)
GPU NVIDIA Ampere architecture with 1024 NVIDIA® CUDA® cores and 32 Tensor Cores
Max GPU Freq 765 MHz 918 MHz
CPU 6-core Arm® Cortex®-A78AE v8.2 64-bit 8-core Arm® Cortex®-A78AE v8.2 64-bit
CPU Max Freq 2 GHz
Memory 8GB 128-bit LPDDR5 102 GB/s 16GB 128-bit LPDDR5 102 GB/s
Storage No internal storage included, supports NVMe external via PCIe x2 or x4
Deep Learning Accelerator 1x NVDLA v2.0 2x NVDLA v2.0
DLA Max Frequency 610 MHz 614 MHz
Vision Accelerator PVA v2.0 @ 700MHz
Encoder
  • Support for H.264, H.265, VP9 and AV1. For H.265 supports:
  • 1x 8K30
  • 2x 4K60
  • 4x 4K30
  • 9x1080p60
  • 18x1080p30
Decoder
  • Support for H.264, H.265 and AV1. For H.265 supports:
  • 1x 4K60
  • 3x 4K30
  • 6x1080p60
  • 12x1080p30
CSI Camera
  • Up to 8 virtual channels
  • 8 lanes MIPI CSI-2
  • D-PHY 2.1 (up to 20Gbps)




Previous: Introduction Index Next: Introduction/Carrier Boards